AI agents use add_codebase to create or update resources in Claude Context Local — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Context Local environment.
This is a Write operation because it creates or modifies data (adds a codebase to the index) in a reversible manner. It does not execute arbitrary code, delete data, or move money. The severity is medium because misuse could cause excessive indexing overhead or resource consumption on the local system, but the effects are reversible (can be cleared via 'clear_index').
From the tool's definition Tool name 'add_codebase' and description 'Add a codebase to the context for analysis' indicate creation/addition of indexed data to the PostgreSQL backend. This modifies the index state reversibly.
Documented attack patterns abuse exactly the kind of access add_codebase gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Context Local, and nothing reaches the server without passing your rules. This is the rule we recommend for add_codebase:
{
"version": "1",
"default": "deny",
"tools": {
"add_codebase": {
"limits": [
{
"counter": "add_codebase_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_codebase stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add a codebase to the context for analysis. It is categorised as a Write tool in the Claude Context Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Context Local MCP server in PolicyLayer and add a rule for add_codebase: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Context Local. Nothing to install.
add_codebase is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_codebase rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for add_codebase. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
add_codebase is provided by the Claude Context Local MCP server (mikeo-ai/claude-context-local). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Context Local, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Claude Context Local tools catalogued and risk-classified — across an index of 43,000+ MCP servers.